Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to significance and uniqueness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    important qualities or characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.57
     Staates
    -0.54
     Stärke
    -0.53
    :✨
    -0.53
     Justiz
    -0.50
     vectorielle
    -0.49
    Gruss
    -0.49
    onAttach
    -0.48
    ollectionView
    -0.47
    cerpt
    -0.46
    POSITIVE LOGITS
    ','',
    0.41
     desirous
    0.40
     wet
    0.38
    0.37
    icano
    0.37
     serviceable
    0.36
     unsure
    0.36
    JsonFormat
    0.36
     detrimental
    0.35
     hod
    0.35
    Act Density 0.136%

    No Known Activations